Application Of Artificial Neural Network Models To Analyse The Relationships Between Gammarus pulex L. (Crustacea, Amphipoda) And River Characteristics

This study aimed at analysing the relationship between river characteristics and abundance of Gammarus pulex. To this end, four methods which can identify the relative contribution and/or the contribution profile of the input variables in neural networks describing the habitat preferences of this species were compared: (i) the ‘PaD‘ (‘Partial Derivatives‘) method consists of a calculation of the partial derivatives of the output in relation to the input variables; (ii) the ‘Weights‘method is a computation using the connection weights of the backpropagation Artificial Neural Networks; (iii) the ‘Perturb‘method analyses the effect of a perturbation of the input variables on the output variable; (iv) the ‘Profile‘ method is a successive variation of one input variable while the others are kept constant at a fixed set of values. The dataset consisted of 179 samples, collected over a three-year period in the Zwalm river basin in Flanders, Belgium. Twenty-four environmental variables as well as the log-transformed abundance of Gammarus pulex were used in this study. The different contribution methods gave similar results concerning the order of importance of the input variables. Moreover, the stability of the methods was confirmed by gradually removing variables. Only in a limited number of cases a shift in the relative importance of the remaining input variables could be observed. Nevertheless, differences in sensitivity and stability of the methods were detected, probably as a result of the different calculation procedures. In this respect, the ‘PaD‘method made a more severe discrimination between minor and major contributing environmental variables in comparison to the ‘Weights‘, ‘Profile‘ and ‘Perturb‘ methods. From an ecological point of view, the input variables ‘Ammonium‘ and to a smaller extent ‘COD‘, were selected by these methods as dominant river characteristics for the prediction of the abundance of Gammarus pulex in this study area.

[1]  Colin R. Townsend,et al.  Habitat scale and biodiversity: influence of catchment, stream reach and bedform scales on local invertebrate diversity , 2003, Biodiversity & Conservation.

[2]  I. Dimopoulos,et al.  Role of some environmental variables in trout abundance models using neural networks , 1996 .

[3]  Peter Goethals,et al.  DEVELOPMENT OF A CONCEPT FOR INTEGRATED ECOLOGICAL RIVER ASSESSMENT IN FLANDERS, BELGIUM , 2001 .

[4]  James R. Karr,et al.  Biological monitoring: Essential foundation for ecological risk assessment , 1997 .

[5]  Michele Scardi,et al.  Developing an empirical model of phytoplankton primary production: a neural network case study , 1999 .

[6]  Young-Seuk Park,et al.  Implementation of artificial neural networks in patterning and prediction of exergy in response to temporal dynamics of benthic macroinvertebrate communities in streams , 2001 .

[7]  A. T. C. Goh,et al.  Back-propagation neural networks for modeling complex systems , 1995, Artif. Intell. Eng..

[8]  P. G. Whitehead,et al.  Modelling algal growth and transport in rivers: a comparison of time series analysis, dynamic mass balance and neural network techniques , 1997, Hydrobiologia.

[9]  Niels De Pauw,et al.  Microhabitat preference of stream macrobenthos and its significance in water quality assessment , 1994 .

[10]  Friedrich Recknagel,et al.  Relationships between habitat properties and the occurrence of macroinvertebrates in Queensland streams (Australia) discovered by a sensitivity analysis with artificial neural networks , 2002 .

[11]  Niels De Pauw,et al.  Biological monitoring of river water quality , 1994 .

[12]  O. Beauchard,et al.  Macroinvertebrate richness patterns in North African streams , 2003 .

[13]  Sovan Lek,et al.  Stochastic models that predict trout population density or biomass on a mesohabitat scale , 1996, Hydrobiologia.

[14]  N. De Pauw,et al.  Performance of two artificial substrate samplers for macroinvertebrates in biological monitoring of large and deep rivers and canals in Belgium and The Netherlands , 1994, Environmental monitoring and assessment.

[15]  M. Barbour.  The re‐invention of biological assessment in the U.S. , 1997 .

[16]  D. Borchardt,et al.  Bioindication of chemical and hydromorphological habitat characteristics with benthic macro-invertebrates based on Artificial Neural Networks , 2001, Aquatic Ecology.

[17]  G. David Garson,et al.  Interpreting neural-network connection weights , 1991 .

[18]  Peter Goethals,et al.  Optimization of Artificial Neural Network (ANN) model design for prediction of macroinvertebrates in the Zwalm river basin (Flanders, Belgium) , 2004 .

[19]  M. Bournaud,et al.  Les microhabitats aquatiques des rives d'un grand cours d'eau : approche faunistique , 1986 .

[20]  Friedrich Recknagel,et al.  Predictive modelling of macroinvertebrate assemblages for stream habitat assessments in Queensland (Australia) , 2001 .

[21]  T. Dapper,et al.  The influence of environmental variables on the abundance of aquatic insects: a comparison of ordination and artificial neural networks , 2000, Hydrobiologia.

[22]  I. Dimopoulos,et al.  Application of neural networks to modelling nonlinear relationships in ecology , 1996 .

[23]  M. Gevrey,et al.  Review and comparison of methods to study the contribution of variables in artificial neural network models , 2003 .

[24]  Robert J. Naiman,et al.  Disturbance regimes, resilience, and recovery of animal communities and habitats in lotic ecosystems , 1990 .

[25]  J. Meyer.  Stream Health: Incorporating the Human Dimension to Advance Stream Ecology , 1997, Journal of the North American Benthological Society.

[26]  G. W. Minshall,et al.  Factors affecting microdistribution of stream benthic insects , 1977 .

[27]  Sovan Lek,et al.  Abundance, diversity, and structure of freshwater invertebrates and fish communities: An artificial neural network approach , 2001 .

[28]  I. Dimopoulos,et al.  Neural network models to study relationships between lead concentration in grasses and permanent urban descriptors in Athens city (Greece) , 1999 .

[29]  Jaimie T A Dick,et al.  The validity of the Gammarus:Asellus ratio as an index of organic pollution: abiotic and biotic influences. , 2002, Water research.

[30]  Ian T. Whitehurst,et al.  The impact of organic enrichment on the benthic macroinvertebrate communities of a lowland river , 1990 .

[31]  Sovan Lek,et al.  Improved estimation, using neural networks, of the food consumption of fish populations , 1995 .

[32]  Niels De Pauw,et al.  Comparison of Artificial Neural Network (ANN) Model Development Methods for Prediction of Macroinvertebrate Communities in the Zwalm River Basin in Flanders, Belgium , 2002, TheScientificWorldJournal.

[33]  Jingtao Yao,et al.  Forecasting and Analysis of Marketing Data Using Neural Networks , 1998, J. Inf. Sci. Eng..

[34]  Niels De Pauw,et al.  Method for biological quality assessment of watercourses in Belgium , 2004, Hydrobiologia.

[35]  S. Lek,et al.  Applications of artificial neural networks for patterning and predicting aquatic insect species richness in running waters , 2003 .

[36]  C. Wesenberg-Lund,et al.  Biologie der Süsswassertiere: Wirbellose Tiere , 1939 .

[37]  Julian D. Olden,et al.  Illuminating the “black box”: a randomization approach for understanding variable contributions in artificial neural networks , 2002 .

[38]  Ian Witten,et al.  Data Mining , 2000 .

[39]  Geoffrey E. Hinton,et al.  Learning representations by back-propagation errors, nature , 1986 .

[40]  Susan M. Cormier,et al.  Methods Development and use of Macroinvertebrates as Indicators of Ecological Conditions for Streams in the Mid-Atlantic Highlands Region , 2002, Environmental monitoring and assessment.

[41]  Yannis Dimopoulos,et al.  Use of some sensitivity criteria for choosing networks with good generalization ability , 1995, Neural Processing Letters.

[42]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[43]  Sovan Lek,et al.  Artificial neural networks as a tool in ecological modelling, an introduction , 1999 .

[44]  Peter Goethals,et al.  Genetic algorithms for optimisation of predictive ecosystems models based on decision trees and neural networks , 2006 .

[45]  Young-Seuk Park,et al.  Patterning and predicting aquatic macroinvertebrate diversities using artificial neural network. , 2003, Water research.

[46]  Sovan Lek,et al.  Energy availability and habitat heterogeneity predict global riverine fish diversity , 1998, Nature.

[47]  S. Lek,et al.  The use of artificial neural networks to predict the presence of small‐bodied fish in a river , 1997 .

[48]  W. J. Walley,et al.  Neural network predictors of average score per taxon and number of families at unpolluted river sites in Great Britain , 1998 .

[49]  P. Goethals,et al.  Use of genetic algorithms to select input variables in decision tree models for the prediction of benthic macroinvertebrates , 2003 .

[50]  Ingrid M. Schleiter,et al.  Modelling water quality, bioindication and population dynamics in lotic ecosystems using neural networks , 1999 .

[51]  Arthur V. Brown,et al.  The Role of Disturbance in Stream Ecology , 1988, Journal of the North American Benthological Society.

[52]  Wayne S. Davis,et al.  Biological assessment and criteria : tools for water resource planning and decision making , 1995 .

[53]  Mike R. Scarsbrook,et al.  Quantifying Disturbance in Streams: Alternative Measures of Disturbance in Relation to Macroinvertebrate Species Traits and Species Richness , 1997, Journal of the North American Benthological Society.